Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2898 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.5634. Min Act: -0.1700

Data Index: 4306155 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.5142. Min Act: -0.1700

Data Index: 4946396 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.5058. Min Act: -0.1700

Data Index: 1397125 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.4361. Min Act: -0.1700

Data Index: 168690 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3906. Min Act: -0.1700

Data Index: 7079170 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3930. Min Act: -0.1700

Data Index: 109016 (Open Web Text)

Max Activating Token Index: 303

Text #6

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.4275. Min Act: -0.1700

Data Index: 800578 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3641. Min Act: -0.1700

Data Index: 5155956 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3661. Min Act: -0.1700

Data Index: 2960863 (Open Web Text)

Max Activating Token Index: 134

Text #9

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.4036. Min Act: -0.1700

Data Index: 2063297 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3852. Min Act: -0.1700

Data Index: 6126071 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3495. Min Act: -0.1700

Data Index: 7224950 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3486. Min Act: -0.1700

Data Index: 5229774 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3180. Min Act: -0.1700

Data Index: 3370954 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.3170. Min Act: -0.1700

Data Index: 1121044 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.2951. Min Act: -0.1700

Data Index: 6214776 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.2746. Min Act: -0.1700

Data Index: 876877 (Open Web Text)

Max Activating Token Index: 165

Text #17

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.2703. Min Act: -0.1700

Data Index: 1836414 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.2533. Min Act: -0.1700

Data Index: 6078981 (Open Web Text)

Max Activating Token Index: 243

Text #19

Max Range: 5.5634. Min Range: -5.5634

Max Act: 5.2117. Min Act: -0.1700

Data Index: 7017447 (Open Web Text)

Max Activating Token Index: 647